Sensor fusion of mobile mapping data for road management using machine/deep learning

ACQUAL

Potential supervisors

Ville Lehtola, Shayan Nikoohemat (UT Post Doc, Kaios)

Spatial Engineering

This topic is not adaptable to Spatial Engineering

Suggested Electives

Advanced image analysis, Laser scanning 201800310, Positioning and Imaging Technology 201700167, Programming courses (python)

Additional Remarks

Students should have suitable programming skills (Python/c++). The research is done in collaboration with a company, Kaios. Internship options can be discussed.

Description

Roads are important assets for the society, and the public sector is responsible for their upkeep. To make the road management more effective, mobile mapping data (LIDAR, RGB) is gathered and then processed to obtain the current condition of the scanned roads. However, the processing part has several challenges. Therefore, this topic is focused on the detection and classification of road markings and the road condition (e.g. unevenness, notable potholes or cracks). The data set will be available for the student in August for the detailed development of the proposal. This MSc research is done in collaboration with a company, Kaois. Internship option is available.

Objectives and Methodology

Machine/deep learning approaches for sensor fusion, object detection, object classification, and object localization methods applied on RGB images and 3D point clouds

Further reading